I developed a new model for retail selection assortment optimization, specifically to address efficient exploration of products with limited demand signals.

I was a founding member of the Amazon Machine Learning Solutions Lab, a program to bring cutting-edge AI/ML solutions to AWS customers in telecom, finance, manufacturing, energy, transportation industry verticals.I designed and developed novel Machine Learning solutions for AWS Customers (National Hockey League, Verizon, Conoco Philips, Shell, Grab, Formosa, DLink, iFit, National Australia Bank and VFS).I led a small team to develop and open source a set of example templates to accelerate the delivery of custom ML solutions to production called ML Max (https://github.com/awslabs/mlmax/).I led research for the technical report: *Quantifying Uncertainty in Deep Learning Systems* https://d1.awsstatic.com/APG/quantifying-uncertainty-in-deep-learning-systems.pdf

Data Scientist for the San Francisco office, directing and executing technical aspects of data science projects, presenting regularly to senior-clients, mentoring junior data scientists, and providing expert contributions to business development efforts.

One-on-one mentor for Springboard's (formerly SlideRule) "Data Science Intensive", covering the entire data science pipeline in Python.Information: https://www.mysliderule.com/workshops/data-science-intensive/

Co-instructor for the 66-hour course on Data Science. Course covers complete data science pipeline with a focus on predictive analytics in Python. Instructor for workshops covering foundational aspects of data science in Python.Course Info: https://generalassemb.ly/education/data-science

Provide high-leverage quantitative services including predictive modeling, process improvement, performance management, data visualization and data engineering.

Conducted analysis on the operational quality of the supply base for the Joint Strike Fighter (JSF) airframe. Authored major revision of manufacturing policy estimated to save 1,400 work hours annually (based on internal estimates).

Analyzed the costs and benefits associated with the construction of a dedicated return center for Johnson and Johnson's supply chain organization. Return center proposal was accepted on the basis of the analysis and is estimated to reduce costs by $3M annually.